In [ ]:
!pip install plotly numpy pandas
Requirement already satisfied: plotly in c:\users\looper\appdata\local\programs\python\python311\lib\site-packages (5.18.0) Requirement already satisfied: numpy in c:\users\looper\appdata\local\programs\python\python311\lib\site-packages (1.26.2) Requirement already satisfied: pandas in c:\users\looper\appdata\local\programs\python\python311\lib\site-packages (2.1.4) Requirement already satisfied: tenacity>=6.2.0 in c:\users\looper\appdata\local\programs\python\python311\lib\site-packages (from plotly) (8.2.3) Requirement already satisfied: packaging in c:\users\looper\appdata\local\programs\python\python311\lib\site-packages (from plotly) (23.2) Requirement already satisfied: python-dateutil>=2.8.2 in c:\users\looper\appdata\local\programs\python\python311\lib\site-packages (from pandas) (2.8.2) Requirement already satisfied: pytz>=2020.1 in c:\users\looper\appdata\local\programs\python\python311\lib\site-packages (from pandas) (2023.3.post1) Requirement already satisfied: tzdata>=2022.1 in c:\users\looper\appdata\local\programs\python\python311\lib\site-packages (from pandas) (2023.3) Requirement already satisfied: six>=1.5 in c:\users\looper\appdata\local\programs\python\python311\lib\site-packages (from python-dateutil>=2.8.2->pandas) (1.16.0)
[notice] A new release of pip available: 22.3.1 -> 23.3.2 [notice] To update, run: C:\Users\Looper\AppData\Local\Programs\Python\Python311\python.exe -m pip install --upgrade pip
In [ ]:
import pandas as pd
import numpy as np
import plotly.express as px
data= pd.read_csv("spotify-2023.csv")
data['streams'] = pd.to_numeric(data['streams'], errors='coerce')
In [ ]:
most_streamed = data.loc[data.groupby('released_year')['streams'].idxmax()]
clean_data = most_streamed[['track_name', 'artist(s)_name', 'released_year', 'streams']]
fig = px.bar(clean_data, x='released_year', y='streams')
fig.show(renderer='notebook')
In [ ]:
top_songs = data.groupby('released_year').apply(lambda group: group.nlargest(3, 'streams')).reset_index(drop=True)
top_songs = top_songs[['track_name', 'artist(s)_name', 'released_year', 'streams']]
top_songs = top_songs.query("""released_year >= 2010""")
fig = px.bar(top_songs, x='released_year' , y='streams', hover_data=['track_name', 'artist(s)_name'], color_continuous_scale="Agsunset", color="streams", title='Top 3 streamed Songs ny year' )
fig.show(renderer='notebook')
In [ ]:
song_keys = data[["released_year","key","streams"]]
song_keys["count"] = song_keys.apply(lambda x:1, axis=1)
group = song_keys.groupby('key')['streams'].sum().reset_index()
def to_millions(x):
return x / 1e6
group["value_in_millions"] = group["streams"].apply(to_millions)
fig = px.pie(group, values="value_in_millions", names="key", title="Key Share in songs")
fig.show(renderer='notebook')
C:\Users\Looper\AppData\Local\Temp\ipykernel_10764\2075218377.py:2: SettingWithCopyWarning: A value is trying to be set on a copy of a slice from a DataFrame. Try using .loc[row_indexer,col_indexer] = value instead See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy